To efficiently restore the vibration signals of a phase-sensitive optical time domain reflectometer (Φ-OTDR), the GF-FastICA joint algorithm is proposed, which combines guided filtering with fast independent component analysis (FastICA). The marked region of vibration is precisely located by guided filtering. FastICA deals with the optimal phase mixing matrix of the marked region to separate the vibration signals from the noise-containing phase signals. The experimental results show that the GF-FastICA achieves a correlation coefficient of 0.998 for 5-Hz vibration signal recovery from a 14.3-km sensing fiber, verifying the potency of the algorithm. Compared with the traditional method and FastICA only, GF-FastICA improves the root mean square error (RMSE) metric by an order of magnitude, which is approaching an experience value of 10-3.